VM_SHADOW_STACK (alias to VM_HIGH_ARCH_5) is used to encode shadow stack VMA on three architectures (x86 shadow stack, arm GCS and RISC-V shadow stack). In case architecture doesn't implement shadow stack, it's VM_NONE Introducing a helper `is_shadow_stack_vma` to determine shadow stack vma or not.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- mm/gup.c | 2 +- mm/vma.h | 10 +++++++--- 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c index a82890b46a36..8e6e14179f6c 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1282,7 +1282,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) !writable_file_mapping_allowed(vma, gup_flags)) return -EFAULT;

- if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { + if (!(vm_flags & VM_WRITE) || is_shadow_stack_vma(vm_flags)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */ diff --git a/mm/vma.h b/mm/vma.h index 819f994cf727..0f238dc37231 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -357,7 +357,7 @@ static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi, }

/* - * These three helpers classifies VMAs for virtual memory accounting. + * These four helpers classifies VMAs for virtual memory accounting. */

/* @@ -368,6 +368,11 @@ static inline bool is_exec_mapping(vm_flags_t flags) return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; }

+static inline bool is_shadow_stack_vma(vm_flags_t vm_flags) +{ + return !!(vm_flags & VM_SHADOW_STACK); +} + /* * Stack area (including shadow stacks) * @@ -376,7 +381,7 @@ static inline bool is_exec_mapping(vm_flags_t flags) */ static inline bool is_stack_mapping(vm_flags_t flags) { - return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK); + return ((flags & VM_STACK) == VM_STACK) || is_shadow_stack_vma(flags); }

/* @@ -387,7 +392,6 @@ static inline bool is_data_mapping(vm_flags_t flags) return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; }

- static inline void vma_iter_config(struct vma_iterator *vmi, unsigned long index, unsigned long last) {

From: Samuel Holland samuel.holland@sifive.com

Some bits in the [ms]envcfg CSR, such as the CFI state and pointer masking mode, need to be controlled on a per-thread basis. Support this by keeping a copy of the CSR value in struct thread_struct and writing it during context switches. It is safe to discard the old CSR value during the context switch because the CSR is modified only by software, so the CSR will remain in sync with the copy in thread_struct.

Use ALTERNATIVE directly instead of riscv_has_extension_unlikely() to minimize branchiness in the context switching code.

Since thread_struct is copied during fork(), setting the value for the init task sets the default value for all other threads.

Reviewed-by: Andrew Jones ajones@ventanamicro.com Reviewed-by: Deepak Gupta debug@rivosinc.com Signed-off-by: Samuel Holland samuel.holland@sifive.com --- arch/riscv/include/asm/switch_to.h | 8 ++++++++ arch/riscv/include/asm/thread_info.h | 1 + arch/riscv/kernel/cpufeature.c | 2 +- 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 7594df37cc9f..dd4a36ff4356 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -70,6 +70,13 @@ static __always_inline bool has_fpu(void) { return false; } #define __switch_to_fpu(__prev, __next) do { } while (0) #endif

+static inline void __switch_to_envcfg(struct task_struct *next) +{ + asm volatile (ALTERNATIVE("nop", "csrw " __stringify(CSR_ENVCFG) ", %0", + 0, RISCV_ISA_EXT_XLINUXENVCFG, 1) + :: "r" (next->thread_info.envcfg) : "memory"); +} + extern struct task_struct *__switch_to(struct task_struct *, struct task_struct *);

@@ -103,6 +110,7 @@ do { \ __switch_to_vector(__prev, __next); \ if (switch_to_should_flush_icache(__next)) \ local_flush_icache_all(); \ + __switch_to_envcfg(__next); \ ((last) = __switch_to(__prev, __next)); \ } while (0)

diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index ebe52f96da34..e494871071da 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -57,6 +57,7 @@ struct thread_info { long user_sp; /* User stack pointer */ int cpu; unsigned long syscall_work; /* SYSCALL_WORK_ flags */ + unsigned long envcfg; #ifdef CONFIG_SHADOW_CALL_STACK void *scs_base; void *scs_sp; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index e560a253e99b..c0986291696a 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -923,7 +923,7 @@ unsigned long riscv_get_elf_hwcap(void) void riscv_user_isa_enable(void) { if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOZ)) - csr_set(CSR_ENVCFG, ENVCFG_CBZE); + current->thread_info.envcfg |= ENVCFG_CBZE; else if (any_cpu_has_zicboz) pr_warn_once("Zicboz disabled as it is unavailable on some harts\n"); }

riscv will need an implementation for exit_thread to clean up shadow stack when thread exits. If current thread had shadow stack enabled, shadow stack is allocated by default for any new thread.

Signed-off-by: Deepak Gupta debug@rivosinc.com Reviewed-by: Charlie Jenkins charlie@rivosinc.com --- arch/riscv/Kconfig | 1 + arch/riscv/kernel/process.c | 5 +++++ 2 files changed, 6 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 22dc5ea4196c..808ea66b9537 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -182,6 +182,7 @@ config RISCV select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS + select HAVE_EXIT_THREAD select HOTPLUG_CORE_SYNC_DEAD if HOTPLUG_CPU select IRQ_DOMAIN select IRQ_FORCED_THREADING diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index e3142d8a6e28..1f2574fb2edb 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -201,6 +201,11 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; }

+void exit_thread(struct task_struct *tsk) +{ + +} + int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags;

zicfiss and zicfilp extension gets enabled via b3 and b2 in *envcfg CSR. menvcfg controls enabling for S/HS mode. henvcfg control enabling for VS while senvcfg controls enabling for U/VU mode.

zicfilp extension extends *status CSR to hold `expected landing pad` bit. A trap or interrupt can occur between an indirect jmp/call and target instr. `expected landing pad` bit from CPU is recorded into xstatus CSR so that when supervisor performs xret, `expected landing pad` state of CPU can be restored.

zicfiss adds one new CSR - CSR_SSP: CSR_SSP contains current shadow stack pointer.

Signed-off-by: Deepak Gupta debug@rivosinc.com Reviewed-by: Charlie Jenkins charlie@rivosinc.com --- arch/riscv/include/asm/csr.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)

diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 25966995da04..af7ed9bedaee 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -18,6 +18,15 @@ #define SR_MPP _AC(0x00001800, UL) /* Previously Machine */ #define SR_SUM _AC(0x00040000, UL) /* Supervisor User Memory Access */

+/* zicfilp landing pad status bit */ +#define SR_SPELP _AC(0x00800000, UL) +#define SR_MPELP _AC(0x020000000000, UL) +#ifdef CONFIG_RISCV_M_MODE +#define SR_ELP SR_MPELP +#else +#define SR_ELP SR_SPELP +#endif + #define SR_FS _AC(0x00006000, UL) /* Floating-point Status */ #define SR_FS_OFF _AC(0x00000000, UL) #define SR_FS_INITIAL _AC(0x00002000, UL) @@ -197,6 +206,8 @@ #define ENVCFG_PBMTE (_AC(1, ULL) << 62) #define ENVCFG_CBZE (_AC(1, UL) << 7) #define ENVCFG_CBCFE (_AC(1, UL) << 6) +#define ENVCFG_LPE (_AC(1, UL) << 2) +#define ENVCFG_SSE (_AC(1, UL) << 3) #define ENVCFG_CBIE_SHIFT 4 #define ENVCFG_CBIE (_AC(0x3, UL) << ENVCFG_CBIE_SHIFT) #define ENVCFG_CBIE_ILL _AC(0x0, UL) @@ -215,6 +226,11 @@ #define SMSTATEEN0_HSENVCFG (_ULL(1) << SMSTATEEN0_HSENVCFG_SHIFT) #define SMSTATEEN0_SSTATEEN0_SHIFT 63 #define SMSTATEEN0_SSTATEEN0 (_ULL(1) << SMSTATEEN0_SSTATEEN0_SHIFT) +/* + * zicfiss user mode csr + * CSR_SSP holds current shadow stack pointer. + */ +#define CSR_SSP 0x011

/* symbolic CSR names: */ #define CSR_CYCLE 0xc00

`arch_calc_vm_prot_bits` is implemented on risc-v to return VM_READ | VM_WRITE if PROT_WRITE is specified. Similarly `riscv_sys_mmap` is updated to convert all incoming PROT_WRITE to (PROT_WRITE | PROT_READ). This is to make sure that any existing apps using PROT_WRITE still work.

Earlier `protection_map[VM_WRITE]` used to pick read-write PTE encodings. Now `protection_map[VM_WRITE]` will always pick PAGE_SHADOWSTACK PTE encodings for shadow stack. Above changes ensure that existing apps continue to work because underneath kernel will be picking `protection_map[VM_WRITE|VM_READ]` PTE encodings.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/mman.h | 24 ++++++++++++++++++++++++ arch/riscv/include/asm/pgtable.h | 1 + arch/riscv/kernel/sys_riscv.c | 10 ++++++++++ arch/riscv/mm/init.c | 2 +- mm/mmap.c | 1 + 5 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/mman.h b/arch/riscv/include/asm/mman.h new file mode 100644 index 000000000000..ef9fedf32546 --- /dev/null +++ b/arch/riscv/include/asm/mman.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include <linux/compiler.h> +#include <linux/types.h> +#include <uapi/asm/mman.h> + +static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, + unsigned long pkey __always_unused) +{ + unsigned long ret = 0; + + /* + * If PROT_WRITE was specified, force it to VM_READ | VM_WRITE. + * Only VM_WRITE means shadow stack. + */ + if (prot & PROT_WRITE) + ret = (VM_READ | VM_WRITE); + return ret; +} +#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) + +#endif /* ! __ASM_MMAN_H__ */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index e79f15293492..4948a1f18ae8 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -177,6 +177,7 @@ extern struct pt_alloc_ops pt_ops __meminitdata; #define PAGE_READ_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) #define PAGE_WRITE_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | \ _PAGE_EXEC | _PAGE_WRITE) +#define PAGE_SHADOWSTACK __pgprot(_PAGE_BASE | _PAGE_WRITE)

#define PAGE_COPY PAGE_READ #define PAGE_COPY_EXEC PAGE_READ_EXEC diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index d77afe05578f..43a448bf254b 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -7,6 +7,7 @@

#include <linux/syscalls.h> #include <asm/cacheflush.h> +#include <asm-generic/mman-common.h>

static long riscv_sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, @@ -16,6 +17,15 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL;

+ /* + * If PROT_WRITE is specified then extend that to PROT_READ + * protection_map[VM_WRITE] is now going to select shadow stack encodings. + * So specifying PROT_WRITE actually should select protection_map [VM_WRITE | VM_READ] + * If user wants to create shadow stack then they should use `map_shadow_stack` syscall. + */ + if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ))) + prot |= PROT_READ; + return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 0e8c20adcd98..964810aeb405 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -326,7 +326,7 @@ pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); static const pgprot_t protection_map[16] = { [VM_NONE] = PAGE_NONE, [VM_READ] = PAGE_READ, - [VM_WRITE] = PAGE_COPY, + [VM_WRITE] = PAGE_SHADOWSTACK, [VM_WRITE | VM_READ] = PAGE_COPY, [VM_EXEC] = PAGE_EXEC, [VM_EXEC | VM_READ] = PAGE_READ_EXEC, diff --git a/mm/mmap.c b/mm/mmap.c index dd4b35a25aeb..b56f1e8cbfc6 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -47,6 +47,7 @@ #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/ksm.h> +#include <linux/processor.h>

#include <linux/uaccess.h> #include <asm/cacheflush.h>

pte_mkwrite creates PTEs with WRITE encodings for underlying arch. Underlying arch can have two types of writeable mappings. One that can be written using regular store instructions. Another one that can only be written using specialized store instructions (like shadow stack stores). pte_mkwrite can select write PTE encoding based on VMA range (i.e. VM_SHADOW_STACK)

Signed-off-by: Deepak Gupta debug@rivosinc.com Reviewed-by: Alexandre Ghiti alexghiti@rivosinc.com --- arch/riscv/include/asm/pgtable.h | 7 +++++++ arch/riscv/mm/pgtable.c | 17 +++++++++++++++++ 2 files changed, 24 insertions(+)

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 2c6edc8d04a3..7963ab11d924 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -416,6 +416,10 @@ static inline pte_t pte_wrprotect(pte_t pte)

/* static inline pte_t pte_mkread(pte_t pte) */

+struct vm_area_struct; +pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma); +#define pte_mkwrite pte_mkwrite + static inline pte_t pte_mkwrite_novma(pte_t pte) { return __pte(pte_val(pte) | _PAGE_WRITE); @@ -738,6 +742,9 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) return pte_pmd(pte_mkyoung(pmd_pte(pmd))); }

+pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); +#define pmd_mkwrite pmd_mkwrite + static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) { return pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))); diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c index 4ae67324f992..be5d38546bb3 100644 --- a/arch/riscv/mm/pgtable.c +++ b/arch/riscv/mm/pgtable.c @@ -155,3 +155,20 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, return pmd; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_SHADOW_STACK) + return pte_mkwrite_shstk(pte); + + return pte_mkwrite_novma(pte); +} + +pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_SHADOW_STACK) + return pmd_mkwrite_shstk(pmd); + + return pmd_mkwrite_novma(pmd); +} +

As discussed extensively in the changelog for the addition of this syscall on x86 ("x86/shstk: Introduce map_shadow_stack syscall") the existing mmap() and madvise() syscalls do not map entirely well onto the security requirements for shadow stack memory since they lead to windows where memory is allocated but not yet protected or stacks which are not properly and safely initialised. Instead a new syscall map_shadow_stack() has been defined which allocates and initialises a shadow stack page.

This patch implements this syscall for riscv. riscv doesn't require token to be setup by kernel because user mode can do that by itself. However to provide compatibility and portability with other architectues, user mode can specify token set flag.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/kernel/Makefile | 2 + arch/riscv/kernel/usercfi.c | 145 ++++++++++++++++++++++++++++++++++++++++ include/uapi/asm-generic/mman.h | 4 ++ 3 files changed, 151 insertions(+)

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 7f88cc4931f5..eb2c94dd0a9d 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -117,3 +117,5 @@ obj-$(CONFIG_COMPAT) += compat_vdso/ obj-$(CONFIG_64BIT) += pi/ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o + +obj-$(CONFIG_RISCV_USER_CFI) += usercfi.o diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c new file mode 100644 index 000000000000..ce002eabbdc1 --- /dev/null +++ b/arch/riscv/kernel/usercfi.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Rivos, Inc. + * Deepak Gupta debug@rivosinc.com + */ + +#include <linux/sched.h> +#include <linux/bitops.h> +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/uaccess.h> +#include <linux/sizes.h> +#include <linux/user.h> +#include <linux/syscalls.h> +#include <linux/prctl.h> +#include <asm/csr.h> +#include <asm/usercfi.h> + +#define SHSTK_ENTRY_SIZE sizeof(void *) + +/* + * Writes on shadow stack can either be `sspush` or `ssamoswap`. `sspush` can happen + * implicitly on current shadow stack pointed to by CSR_SSP. `ssamoswap` takes pointer to + * shadow stack. To keep it simple, we plan to use `ssamoswap` to perform writes on shadow + * stack. + */ +static noinline unsigned long amo_user_shstk(unsigned long *addr, unsigned long val) +{ + /* + * Never expect -1 on shadow stack. Expect return addresses and zero + */ + unsigned long swap = -1; + + __enable_user_access(); + asm goto( + ".option push\n" + ".option arch, +zicfiss\n" + "1: ssamoswap.d %[swap], %[val], %[addr]\n" + _ASM_EXTABLE(1b, %l[fault]) + RISCV_ACQUIRE_BARRIER + ".option pop\n" + : [swap] "=r" (swap), [addr] "+A" (*addr) + : [val] "r" (val) + : "memory" + : fault + ); + __disable_user_access(); + return swap; +fault: + __disable_user_access(); + return -1; +} + +/* + * Create a restore token on the shadow stack. A token is always XLEN wide + * and aligned to XLEN. + */ +static int create_rstor_token(unsigned long ssp, unsigned long *token_addr) +{ + unsigned long addr; + + /* Token must be aligned */ + if (!IS_ALIGNED(ssp, SHSTK_ENTRY_SIZE)) + return -EINVAL; + + /* On RISC-V we're constructing token to be function of address itself */ + addr = ssp - SHSTK_ENTRY_SIZE; + + if (amo_user_shstk((unsigned long __user *)addr, (unsigned long) ssp) == -1) + return -EFAULT; + + if (token_addr) + *token_addr = addr; + + return 0; +} + +static unsigned long allocate_shadow_stack(unsigned long addr, unsigned long size, + unsigned long token_offset, + bool set_tok) +{ + int flags = MAP_ANONYMOUS | MAP_PRIVATE; + struct mm_struct *mm = current->mm; + unsigned long populate, tok_loc = 0; + + if (addr) + flags |= MAP_FIXED_NOREPLACE; + + mmap_write_lock(mm); + addr = do_mmap(NULL, addr, size, PROT_READ, flags, + VM_SHADOW_STACK | VM_WRITE, 0, &populate, NULL); + mmap_write_unlock(mm); + + if (!set_tok || IS_ERR_VALUE(addr)) + goto out; + + if (create_rstor_token(addr + token_offset, &tok_loc)) { + vm_munmap(addr, size); + return -EINVAL; + } + + addr = tok_loc; + +out: + return addr; +} + +SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags) +{ + bool set_tok = flags & SHADOW_STACK_SET_TOKEN; + unsigned long aligned_size = 0; + + if (!cpu_supports_shadow_stack()) + return -EOPNOTSUPP; + + /* Anything other than set token should result in invalid param */ + if (flags & ~SHADOW_STACK_SET_TOKEN) + return -EINVAL; + + /* + * Unlike other architectures, on RISC-V, SSP pointer is held in CSR_SSP and is available + * CSR in all modes. CSR accesses are performed using 12bit index programmed in instruction + * itself. This provides static property on register programming and writes to CSR can't + * be unintentional from programmer's perspective. As long as programmer has guarded areas + * which perform writes to CSR_SSP properly, shadow stack pivoting is not possible. Since + * CSR_SSP is writeable by user mode, it itself can setup a shadow stack token subsequent + * to allocation. Although in order to provide portablity with other architecture (because + * `map_shadow_stack` is arch agnostic syscall), RISC-V will follow expectation of a token + * flag in flags and if provided in flags, setup a token at the base. + */ + + /* If there isn't space for a token */ + if (set_tok && size < SHSTK_ENTRY_SIZE) + return -ENOSPC; + + if (addr && (addr & (PAGE_SIZE - 1))) + return -EINVAL; + + aligned_size = PAGE_ALIGN(size); + if (aligned_size < size) + return -EOVERFLOW; + + return allocate_shadow_stack(addr, aligned_size, size, set_tok); +} diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h index 57e8195d0b53..9cfb3c1e337d 100644 --- a/include/uapi/asm-generic/mman.h +++ b/include/uapi/asm-generic/mman.h @@ -19,4 +19,8 @@ #define MCL_FUTURE 2 /* lock all future mappings */ #define MCL_ONFAULT 4 /* lock all pages that are faulted in */

+/* Set up a restore token in the shadow stack */ +#define SHADOW_STACK_SET_TOKEN (1ULL << 0) +/* Set up a top of stack marker in the shadow stack */ +#define SHADOW_STACK_SET_MARKER (1ULL << 1) #endif /* __ASM_GENERIC_MMAN_H */

From: Mark Brown broonie@kernel.org

Three architectures (x86, aarch64, riscv) have announced support for shadow stacks with fairly similar functionality. While x86 is using arch_prctl() to control the functionality neither arm64 nor riscv uses that interface so this patch adds arch-agnostic prctl() support to get and set status of shadow stacks and lock the current configuration to prevent further changes, with support for turning on and off individual subfeatures so applications can limit their exposure to features that they do not need. The features are:

- PR_SHADOW_STACK_ENABLE: Tracking and enforcement of shadow stacks, including allocation of a shadow stack if one is not already allocated. - PR_SHADOW_STACK_WRITE: Writes to specific addresses in the shadow stack. - PR_SHADOW_STACK_PUSH: Push additional values onto the shadow stack. - PR_SHADOW_STACK_DISABLE: Allow to disable shadow stack. Note once locked, disable must fail.

These features are expected to be inherited by new threads and cleared on exec(), unknown features should be rejected for enable but accepted for locking (in order to allow for future proofing).

This is based on a patch originally written by Deepak Gupta but later modified by Mark Brown for arm's GCS patch series.

Signed-off-by: Mark Brown broonie@kernel.org Co-developed-by: Deepak Gupta debug@rivosinc.com --- include/linux/mm.h | 3 +++ include/uapi/linux/prctl.h | 21 +++++++++++++++++++++ kernel/sys.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 54 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h index 57533b9cae95..54e2b3f1cc30 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4146,6 +4146,9 @@ static inline bool pfn_is_unaccepted_memory(unsigned long pfn) { return range_contains_unaccepted_memory(pfn << PAGE_SHIFT, PAGE_SIZE); } +int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); +int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); +int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);

void vma_pgtable_walk_begin(struct vm_area_struct *vma); void vma_pgtable_walk_end(struct vm_area_struct *vma); diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 35791791a879..b8d7b6361754 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -327,5 +327,26 @@ struct prctl_mm_map { # define PR_PPC_DEXCR_CTRL_SET_ONEXEC 0x8 /* Set the aspect on exec */ # define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ # define PR_PPC_DEXCR_CTRL_MASK 0x1f +/* + * Get the current shadow stack configuration for the current thread, + * this will be the value configured via PR_SET_SHADOW_STACK_STATUS. + */ +#define PR_GET_SHADOW_STACK_STATUS 74 + +/* + * Set the current shadow stack configuration. Enabling the shadow + * stack will cause a shadow stack to be allocated for the thread. + */ +#define PR_SET_SHADOW_STACK_STATUS 75 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) +# define PR_SHADOW_STACK_WRITE (1UL << 1) +# define PR_SHADOW_STACK_PUSH (1UL << 2) + +/* + * Prevent further changes to the specified shadow stack + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_SHADOW_STACK_STATUS 76

#endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 4da31f28fda8..3d38a9c7c5c9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2324,6 +2324,21 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, return -EINVAL; }

+int __weak arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status) +{ + return -EINVAL; +} + +int __weak arch_set_shadow_stack_status(struct task_struct *t, unsigned long status) +{ + return -EINVAL; +} + +int __weak arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status) +{ + return -EINVAL; +} + #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE)

#ifdef CONFIG_ANON_VMA_NAME @@ -2784,6 +2799,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_RISCV_SET_ICACHE_FLUSH_CTX: error = RISCV_SET_ICACHE_FLUSH_CTX(arg2, arg3); break; + case PR_GET_SHADOW_STACK_STATUS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_get_shadow_stack_status(me, (unsigned long __user *) arg2); + break; + case PR_SET_SHADOW_STACK_STATUS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_set_shadow_stack_status(me, arg2); + break; + case PR_LOCK_SHADOW_STACK_STATUS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_lock_shadow_stack_status(me, arg2); + break; default: error = -EINVAL; break;

Implement architecture agnostic prctls() interface for setting and getting shadow stack status.

prctls implemented are PR_GET_SHADOW_STACK_STATUS, PR_SET_SHADOW_STACK_STATUS and PR_LOCK_SHADOW_STACK_STATUS.

As part of PR_SET_SHADOW_STACK_STATUS/PR_GET_SHADOW_STACK_STATUS, only PR_SHADOW_STACK_ENABLE is implemented because RISCV allows each mode to write to their own shadow stack using `sspush` or `ssamoswap`.

PR_LOCK_SHADOW_STACK_STATUS locks current configuration of shadow stack enabling.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/usercfi.h | 18 ++++++- arch/riscv/kernel/process.c | 8 +++ arch/riscv/kernel/usercfi.c | 107 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 132 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h index 719e28e043c8..52850a2c79cf 100644 --- a/arch/riscv/include/asm/usercfi.h +++ b/arch/riscv/include/asm/usercfi.h @@ -7,6 +7,7 @@

#ifndef __ASSEMBLY__ #include <linux/types.h> +#include <linux/prctl.h>

struct task_struct; struct kernel_clone_args; @@ -14,7 +15,8 @@ struct kernel_clone_args; #ifdef CONFIG_RISCV_USER_CFI struct cfi_status { unsigned long ubcfi_en : 1; /* Enable for backward cfi. */ - unsigned long rsvd : ((sizeof(unsigned long)*8) - 1); + unsigned long ubcfi_locked : 1; + unsigned long rsvd : ((sizeof(unsigned long)*8) - 2); unsigned long user_shdw_stk; /* Current user shadow stack pointer */ unsigned long shdw_stk_base; /* Base address of shadow stack */ unsigned long shdw_stk_size; /* size of shadow stack */ @@ -27,6 +29,12 @@ void set_shstk_base(struct task_struct *task, unsigned long shstk_addr, unsigned unsigned long get_shstk_base(struct task_struct *task, unsigned long *size); void set_active_shstk(struct task_struct *task, unsigned long shstk_addr); bool is_shstk_enabled(struct task_struct *task); +bool is_shstk_locked(struct task_struct *task); +bool is_shstk_allocated(struct task_struct *task); +void set_shstk_lock(struct task_struct *task); +void set_shstk_status(struct task_struct *task, bool enable); + +#define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK (PR_SHADOW_STACK_ENABLE)

#else

@@ -42,6 +50,14 @@ bool is_shstk_enabled(struct task_struct *task);

#define is_shstk_enabled(task) false

+#define is_shstk_locked(task) false + +#define is_shstk_allocated(task) false + +#define set_shstk_lock(task) + +#define set_shstk_status(task, enable) + #endif /* CONFIG_RISCV_USER_CFI */

#endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index f6f58b1ed905..f7dec532657f 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -152,6 +152,14 @@ void start_thread(struct pt_regs *regs, unsigned long pc, regs->epc = pc; regs->sp = sp;

+ /* + * clear shadow stack state on exec. + * libc will set it later via prctl. + */ + set_shstk_status(current, false); + set_shstk_base(current, 0, 0); + set_active_shstk(current, 0); + #ifdef CONFIG_64BIT regs->status &= ~SR_UXL;

diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index 7a7f0b57b2d4..c77abe552c88 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -24,6 +24,16 @@ bool is_shstk_enabled(struct task_struct *task) return task->thread_info.user_cfi_state.ubcfi_en ? true : false; }

+bool is_shstk_allocated(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.shdw_stk_base ? true : false; +} + +bool is_shstk_locked(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.ubcfi_locked ? true : false; +} + void set_shstk_base(struct task_struct *task, unsigned long shstk_addr, unsigned long size) { task->thread_info.user_cfi_state.shdw_stk_base = shstk_addr; @@ -42,6 +52,23 @@ void set_active_shstk(struct task_struct *task, unsigned long shstk_addr) task->thread_info.user_cfi_state.user_shdw_stk = shstk_addr; }

+void set_shstk_status(struct task_struct *task, bool enable) +{ + task->thread_info.user_cfi_state.ubcfi_en = enable ? 1 : 0; + + if (enable) + task->thread_info.envcfg |= ENVCFG_SSE; + else + task->thread_info.envcfg &= ~ENVCFG_SSE; + + csr_write(CSR_ENVCFG, task->thread_info.envcfg); +} + +void set_shstk_lock(struct task_struct *task) +{ + task->thread_info.user_cfi_state.ubcfi_locked = 1; +} + /* * If size is 0, then to be compatible with regular stack we want it to be as big as * regular stack. Else PAGE_ALIGN it and return back @@ -264,3 +291,83 @@ void shstk_release(struct task_struct *tsk) vm_munmap(base, size); set_shstk_base(tsk, 0, 0); } + +int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status) +{ + unsigned long bcfi_status = 0; + + if (!cpu_supports_shadow_stack()) + return -EINVAL; + + /* this means shadow stack is enabled on the task */ + bcfi_status |= (is_shstk_enabled(t) ? PR_SHADOW_STACK_ENABLE : 0); + + return copy_to_user(status, &bcfi_status, sizeof(bcfi_status)) ? -EFAULT : 0; +} + +int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status) +{ + unsigned long size = 0, addr = 0; + bool enable_shstk = false; + + if (!cpu_supports_shadow_stack()) + return -EINVAL; + + /* Reject unknown flags */ + if (status & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK) + return -EINVAL; + + /* bcfi status is locked and further can't be modified by user */ + if (is_shstk_locked(t)) + return -EINVAL; + + enable_shstk = status & PR_SHADOW_STACK_ENABLE; + /* Request is to enable shadow stack and shadow stack is not enabled already */ + if (enable_shstk && !is_shstk_enabled(t)) { + /* shadow stack was allocated and enable request again + * no need to support such usecase and return EINVAL. + */ + if (is_shstk_allocated(t)) + return -EINVAL; + + size = calc_shstk_size(0); + addr = allocate_shadow_stack(0, size, 0, false); + if (IS_ERR_VALUE(addr)) + return -ENOMEM; + set_shstk_base(t, addr, size); + set_active_shstk(t, addr + size); + } + + /* + * If a request to disable shadow stack happens, let's go ahead and release it + * Although, if CLONE_VFORKed child did this, then in that case we will end up + * not releasing the shadow stack (because it might be needed in parent). Although + * we will disable it for VFORKed child. And if VFORKed child tries to enable again + * then in that case, it'll get entirely new shadow stack because following condition + * are true + * - shadow stack was not enabled for vforked child + * - shadow stack base was anyways pointing to 0 + * This shouldn't be a big issue because we want parent to have availability of shadow + * stack whenever VFORKed child releases resources via exit or exec but at the same + * time we want VFORKed child to break away and establish new shadow stack if it desires + * + */ + if (!enable_shstk) + shstk_release(t); + + set_shstk_status(t, enable_shstk); + return 0; +} + +int arch_lock_shadow_stack_status(struct task_struct *task, + unsigned long arg) +{ + /* If shtstk not supported or not enabled on task, nothing to lock here */ + if (!cpu_supports_shadow_stack() || + !is_shstk_enabled(task)) + return -EINVAL; + + set_shstk_lock(task); + + return 0; +}

zicfiss / zicfilp introduces a new exception to priv isa `software check exception` with cause code = 18. This patch implements software check exception.

Additionally it implements a cfi violation handler which checks for code in xtval. If xtval=2, it means that sw check exception happened because of an indirect branch not landing on 4 byte aligned PC or not landing on `lpad` instruction or label value embedded in `lpad` not matching label value setup in `x7`. If xtval=3, it means that sw check exception happened because of mismatch between link register (x1 or x5) and top of shadow stack (on execution of `sspopchk`).

In case of cfi violation, SIGSEGV is raised with code=SEGV_CPERR. SEGV_CPERR was introduced by x86 shadow stack patches.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/asm-prototypes.h | 1 + arch/riscv/include/asm/entry-common.h | 2 ++ arch/riscv/kernel/entry.S | 3 +++ arch/riscv/kernel/traps.c | 42 +++++++++++++++++++++++++++++++++ 4 files changed, 48 insertions(+)

diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index cd627ec289f1..5a27cefd7805 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -51,6 +51,7 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_u); DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); +DECLARE_DO_ERROR_INFO(do_trap_software_check);

asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h index 2293e535f865..4068c7e5452a 100644 --- a/arch/riscv/include/asm/entry-common.h +++ b/arch/riscv/include/asm/entry-common.h @@ -39,4 +39,6 @@ static inline int handle_misaligned_store(struct pt_regs *regs) } #endif

+bool handle_user_cfi_violation(struct pt_regs *regs); + #endif /* _ASM_RISCV_ENTRY_COMMON_H */ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index a1f258fd7bbc..aaef4604d841 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -471,6 +471,9 @@ SYM_DATA_START_LOCAL(excp_vect_table) RISCV_PTR do_page_fault /* load page fault */ RISCV_PTR do_trap_unknown RISCV_PTR do_page_fault /* store page fault */ + RISCV_PTR do_trap_unknown /* cause=16 */ + RISCV_PTR do_trap_unknown /* cause=17 */ + RISCV_PTR do_trap_software_check /* cause=18 is sw check exception */ SYM_DATA_END_LABEL(excp_vect_table, SYM_L_LOCAL, excp_vect_table_end)

#ifndef CONFIG_MMU diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 51ebfd23e007..225b1d198ab6 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -354,6 +354,48 @@ void do_trap_ecall_u(struct pt_regs *regs)

}

+#define CFI_TVAL_FCFI_CODE 2 +#define CFI_TVAL_BCFI_CODE 3 +/* handle cfi violations */ +bool handle_user_cfi_violation(struct pt_regs *regs) +{ + bool ret = false; + unsigned long tval = csr_read(CSR_TVAL); + + if (((tval == CFI_TVAL_FCFI_CODE) && cpu_supports_indirect_br_lp_instr()) || + ((tval == CFI_TVAL_BCFI_CODE) && cpu_supports_shadow_stack())) { + do_trap_error(regs, SIGSEGV, SEGV_CPERR, regs->epc, + "Oops - control flow violation"); + ret = true; + } + + return ret; +} +/* + * software check exception is defined with risc-v cfi spec. Software check + * exception is raised when:- + * a) An indirect branch doesn't land on 4 byte aligned PC or `lpad` + * instruction or `label` value programmed in `lpad` instr doesn't + * match with value setup in `x7`. reported code in `xtval` is 2. + * b) `sspopchk` instruction finds a mismatch between top of shadow stack (ssp) + * and x1/x5. reported code in `xtval` is 3. + */ +asmlinkage __visible __trap_section void do_trap_software_check(struct pt_regs *regs) +{ + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + + /* not a cfi violation, then merge into flow of unknown trap handler */ + if (!handle_user_cfi_violation(regs)) + do_trap_unknown(regs); + + irqentry_exit_to_user_mode(regs); + } else { + /* sw check exception coming from kernel is a bug in kernel */ + die(regs, "Kernel BUG"); + } +} + #ifdef CONFIG_MMU asmlinkage __visible noinstr void do_page_fault(struct pt_regs *regs) {

Save shadow stack pointer in sigcontext structure while delivering signal. Restore shadow stack pointer from sigcontext on sigreturn.

As part of save operation, kernel uses `ssamoswap` to save snapshot of current shadow stack on shadow stack itself (can be called as a save token). During restore on sigreturn, kernel retrieves token from top of shadow stack and validates it. This allows that user mode can't arbitrary pivot to any shadow stack address without having a token and thus provide strong security assurance between signaly delivery and sigreturn window.

Use ABI compatible way of saving/restoring shadow stack pointer into signal stack. This follows what Vector extension, where extra registers are placed in a form of extension header + extension body in the stack. The extension header indicates the size of the extra architectural states plus the size of header itself, and a magic identifier of the extension. Then, the extensions body contains the new architectural states in the form defined by uapi.

Signed-off-by: Andy Chiu andy.chiu@sifive.com Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/asm/usercfi.h | 10 ++++ arch/riscv/include/uapi/asm/ptrace.h | 4 ++ arch/riscv/include/uapi/asm/sigcontext.h | 1 + arch/riscv/kernel/signal.c | 80 ++++++++++++++++++++++++++++++++ arch/riscv/kernel/usercfi.c | 57 +++++++++++++++++++++++ 5 files changed, 152 insertions(+)

diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h index 099204d0cd4a..8da61b005d0a 100644 --- a/arch/riscv/include/asm/usercfi.h +++ b/arch/riscv/include/asm/usercfi.h @@ -8,6 +8,7 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/prctl.h> +#include <linux/errno.h>

struct task_struct; struct kernel_clone_args; @@ -35,6 +36,9 @@ bool is_shstk_locked(struct task_struct *task); bool is_shstk_allocated(struct task_struct *task); void set_shstk_lock(struct task_struct *task); void set_shstk_status(struct task_struct *task, bool enable); +unsigned long get_active_shstk(struct task_struct *task); +int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr); +int save_user_shstk(struct task_struct *tsk, unsigned long *saved_shstk_ptr); bool is_indir_lp_enabled(struct task_struct *task); bool is_indir_lp_locked(struct task_struct *task); void set_indir_lp_status(struct task_struct *task, bool enable); @@ -72,6 +76,12 @@ void set_indir_lp_lock(struct task_struct *task);

#define set_indir_lp_lock(task)

+#define restore_user_shstk(tsk, shstk_ptr) -EINVAL + +#define save_user_shstk(tsk, saved_shstk_ptr) -EINVAL + +#define get_active_shstk(task) 0 + #endif /* CONFIG_RISCV_USER_CFI */

#endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index a38268b19c3d..659ea3af5680 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -127,6 +127,10 @@ struct __riscv_v_regset_state { */ #define RISCV_MAX_VLENB (8192)

+struct __sc_riscv_cfi_state { + unsigned long ss_ptr; /* shadow stack pointer */ +}; + #endif /* __ASSEMBLY__ */

#endif /* _UAPI_ASM_RISCV_PTRACE_H */ diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h index cd4f175dc837..f37e4beffe03 100644 --- a/arch/riscv/include/uapi/asm/sigcontext.h +++ b/arch/riscv/include/uapi/asm/sigcontext.h @@ -10,6 +10,7 @@

/* The Magic number for signal context frame header. */ #define RISCV_V_MAGIC 0x53465457 +#define RISCV_ZICFISS_MAGIC 0x9487 #define END_MAGIC 0x0

/* The size of END signal context header. */ diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 014ac1024b85..77cbc4a01e49 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -22,11 +22,13 @@ #include <asm/vector.h> #include <asm/csr.h> #include <asm/cacheflush.h> +#include <asm/usercfi.h>

unsigned long signal_minsigstksz __ro_after_init;

extern u32 __user_rt_sigreturn[2]; static size_t riscv_v_sc_size __ro_after_init; +static size_t riscv_zicfiss_sc_size __ro_after_init;

#define DEBUG_SIG 0

@@ -139,6 +141,62 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec) return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize); }

+static long save_cfiss_state(struct pt_regs *regs, void __user *sc_cfi) +{ + struct __sc_riscv_cfi_state __user *state = sc_cfi; + unsigned long ss_ptr = 0; + long err = 0; + + if (!IS_ENABLED(CONFIG_RISCV_USER_CFI) || !is_shstk_enabled(current)) + return 0; + + /* + * Save a pointer to shadow stack itself on shadow stack as a form of token. + * A token on shadow gives following properties + * - Safe save and restore for shadow stack switching. Any save of shadow stack + * must have had saved a token on shadow stack. Similarly any restore of shadow + * stack must check the token before restore. Since writing to shadow stack with + * address of shadow stack itself is not easily allowed. A restore without a save + * is quite difficult for an attacker to perform. + * - A natural break. A token in shadow stack provides a natural break in shadow stack + * So a single linear range can be bucketed into different shadow stack segments. Any + * sspopchk will detect the condition and fault to kernel as sw check exception. + */ + err |= save_user_shstk(current, &ss_ptr); + err |= __put_user(ss_ptr, &state->ss_ptr); + if (unlikely(err)) + return -EFAULT; + + return riscv_zicfiss_sc_size; +} + +static long __restore_cfiss_state(struct pt_regs *regs, void __user *sc_cfi) +{ + struct __sc_riscv_cfi_state __user *state = sc_cfi; + unsigned long ss_ptr = 0; + long err; + + /* + * Restore shadow stack as a form of token stored on shadow stack itself as a safe + * way to restore. + * A token on shadow gives following properties + * - Safe save and restore for shadow stack switching. Any save of shadow stack + * must have had saved a token on shadow stack. Similarly any restore of shadow + * stack must check the token before restore. Since writing to shadow stack with + * address of shadow stack itself is not easily allowed. A restore without a save + * is quite difficult for an attacker to perform. + * - A natural break. A token in shadow stack provides a natural break in shadow stack + * So a single linear range can be bucketed into different shadow stack segments. + * sspopchk will detect the condition and fault to kernel as sw check exception. + */ + err = __copy_from_user(&ss_ptr, &state->ss_ptr, sizeof(unsigned long)); + + if (unlikely(err)) + return err; + + return restore_user_shstk(current, ss_ptr); +} + struct arch_ext_priv { __u32 magic; long (*save)(struct pt_regs *regs, void __user *sc_vec); @@ -149,6 +207,10 @@ struct arch_ext_priv arch_ext_list[] = { .magic = RISCV_V_MAGIC, .save = &save_v_state, }, + { + .magic = RISCV_ZICFISS_MAGIC, + .save = &save_cfiss_state, + }, }; const size_t nr_arch_exts = ARRAY_SIZE(arch_ext_list);

@@ -200,6 +262,12 @@ static long restore_sigcontext(struct pt_regs *regs,

err = __restore_v_state(regs, sc_ext_ptr); break; + case RISCV_ZICFISS_MAGIC: + if (!is_shstk_enabled(current) || size != riscv_zicfiss_sc_size) + return -EINVAL; + + err = __restore_cfiss_state(regs, sc_ext_ptr); + break; default: return -EINVAL; } @@ -220,6 +288,10 @@ static size_t get_rt_frame_size(bool cal_all) if (cal_all || riscv_v_vstate_query(task_pt_regs(current))) total_context_size += riscv_v_sc_size; } + + if (is_shstk_enabled(current)) + total_context_size += riscv_zicfiss_sc_size; + /* * Preserved a __riscv_ctx_hdr for END signal context header if an * extension uses __riscv_extra_ext_header @@ -363,6 +435,11 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, #ifdef CONFIG_MMU regs->ra = (unsigned long)VDSO_SYMBOL( current->mm->context.vdso, rt_sigreturn); + + /* if bcfi is enabled x1 (ra) and x5 (t0) must match. not sure if we need this? */ + if (is_shstk_enabled(current)) + regs->t0 = regs->ra; + #else /* * For the nommu case we don't have a VDSO. Instead we push two @@ -491,6 +568,9 @@ void __init init_rt_signal_env(void) { riscv_v_sc_size = sizeof(struct __riscv_ctx_hdr) + sizeof(struct __sc_riscv_v_state) + riscv_v_vsize; + + riscv_zicfiss_sc_size = sizeof(struct __riscv_ctx_hdr) + + sizeof(struct __sc_riscv_cfi_state); /* * Determine the stack space required for guaranteed signal delivery. * The signal_minsigstksz will be populated into the AT_MINSIGSTKSZ entry diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index 8da509afdbe9..40c32258b6ec 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -52,6 +52,11 @@ void set_active_shstk(struct task_struct *task, unsigned long shstk_addr) task->thread_info.user_cfi_state.user_shdw_stk = shstk_addr; }

+unsigned long get_active_shstk(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.user_shdw_stk; +} + void set_shstk_status(struct task_struct *task, bool enable) { task->thread_info.user_cfi_state.ubcfi_en = enable ? 1 : 0; @@ -164,6 +169,58 @@ static int create_rstor_token(unsigned long ssp, unsigned long *token_addr) return 0; }

+/* + * Save user shadow stack pointer on shadow stack itself and return pointer to saved location + * returns -EFAULT if operation was unsuccessful + */ +int save_user_shstk(struct task_struct *tsk, unsigned long *saved_shstk_ptr) +{ + unsigned long ss_ptr = 0; + unsigned long token_loc = 0; + int ret = 0; + + if (saved_shstk_ptr == NULL) + return -EINVAL; + + ss_ptr = get_active_shstk(tsk); + ret = create_rstor_token(ss_ptr, &token_loc); + + if (!ret) { + *saved_shstk_ptr = token_loc; + set_active_shstk(tsk, token_loc); + } + + return ret; +} + +/* + * Restores user shadow stack pointer from token on shadow stack for task `tsk` + * returns -EFAULT if operation was unsuccessful + */ +int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr) +{ + unsigned long token = 0; + + token = amo_user_shstk((unsigned long __user *)shstk_ptr, 0); + + if (token == -1) + return -EFAULT; + + /* invalid token, return EINVAL */ + if ((token - shstk_ptr) != SHSTK_ENTRY_SIZE) { + pr_info_ratelimited( + "%s[%d]: bad restore token in %s: pc=%p sp=%p, token=%p, shstk_ptr=%p\n", + tsk->comm, task_pid_nr(tsk), __func__, + (void *)(task_pt_regs(tsk)->epc), (void *)(task_pt_regs(tsk)->sp), + (void *)token, (void *)shstk_ptr); + return -EINVAL; + } + + /* all checks passed, set active shstk and return success */ + set_active_shstk(tsk, token); + return 0; +} + static unsigned long allocate_shadow_stack(unsigned long addr, unsigned long size, unsigned long token_offset, bool set_tok)

Expose a new register type NT_RISCV_USER_CFI for risc-v cfi status and state. Intentionally both landing pad and shadow stack status and state are rolled into cfi state. Creating two different NT_RISCV_USER_XXX would not be useful and wastage of a note type. Enabling or disabling of feature is not allowed via ptrace set interface. However setting `elp` state or setting shadow stack pointer are allowed via ptrace set interface. It is expected `gdb` might have use to fixup `elp` state or `shadow stack` pointer.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/include/uapi/asm/ptrace.h | 18 ++++++++ arch/riscv/kernel/ptrace.c | 83 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 3 files changed, 102 insertions(+)

diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h index 659ea3af5680..e6571fba8a8a 100644 --- a/arch/riscv/include/uapi/asm/ptrace.h +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -131,6 +131,24 @@ struct __sc_riscv_cfi_state { unsigned long ss_ptr; /* shadow stack pointer */ };

+struct __cfi_status { + /* indirect branch tracking state */ + __u64 lp_en : 1; + __u64 lp_lock : 1; + __u64 elp_state : 1; + + /* shadow stack status */ + __u64 shstk_en : 1; + __u64 shstk_lock : 1; + + __u64 rsvd : sizeof(__u64) - 5; +}; + +struct user_cfi_state { + struct __cfi_status cfi_status; + __u64 shstk_ptr; +}; + #endif /* __ASSEMBLY__ */

#endif /* _UAPI_ASM_RISCV_PTRACE_H */ diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 92731ff8c79a..c69b20ea6e79 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -19,6 +19,7 @@ #include <linux/regset.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> +#include <asm/usercfi.h>

enum riscv_regset { REGSET_X, @@ -28,6 +29,9 @@ enum riscv_regset { #ifdef CONFIG_RISCV_ISA_V REGSET_V, #endif +#ifdef CONFIG_RISCV_USER_CFI + REGSET_CFI, +#endif };

static int riscv_gpr_get(struct task_struct *target, @@ -152,6 +156,75 @@ static int riscv_vr_set(struct task_struct *target, } #endif

+#ifdef CONFIG_RISCV_USER_CFI +static int riscv_cfi_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_cfi_state user_cfi; + struct pt_regs *regs; + + regs = task_pt_regs(target); + + user_cfi.cfi_status.lp_en = is_indir_lp_enabled(target); + user_cfi.cfi_status.lp_lock = is_indir_lp_locked(target); + user_cfi.cfi_status.elp_state = (regs->status & SR_ELP); + + user_cfi.cfi_status.shstk_en = is_shstk_enabled(target); + user_cfi.cfi_status.shstk_lock = is_shstk_locked(target); + user_cfi.shstk_ptr = get_active_shstk(target); + + return membuf_write(&to, &user_cfi, sizeof(user_cfi)); +} + +/* + * Does it make sense to allowing enable / disable of cfi via ptrace? + * Not allowing enable / disable / locking control via ptrace for now. + * Setting shadow stack pointer is allowed. GDB might use it to unwind or + * some other fixup. Similarly gdb might want to suppress elp and may want + * to reset elp state. + */ +static int riscv_cfi_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct user_cfi_state user_cfi; + struct pt_regs *regs; + + regs = task_pt_regs(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_cfi, 0, -1); + if (ret) + return ret; + + /* + * Not allowing enabling or locking shadow stack or landing pad + * There is no disabling of shadow stack or landing pad via ptrace + * rsvd field should be set to zero so that if those fields are needed in future + */ + if (user_cfi.cfi_status.lp_en || user_cfi.cfi_status.lp_lock || + user_cfi.cfi_status.shstk_en || user_cfi.cfi_status.shstk_lock || + !user_cfi.cfi_status.rsvd) + return -EINVAL; + + /* If lpad is enabled on target and ptrace requests to set / clear elp, do that */ + if (is_indir_lp_enabled(target)) { + if (user_cfi.cfi_status.elp_state) /* set elp state */ + regs->status |= SR_ELP; + else + regs->status &= ~SR_ELP; /* clear elp state */ + } + + /* If shadow stack enabled on target, set new shadow stack pointer */ + if (is_shstk_enabled(target)) + set_active_shstk(target, user_cfi.shstk_ptr); + + return 0; +} +#endif + static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { .core_note_type = NT_PRSTATUS, @@ -182,6 +255,16 @@ static const struct user_regset riscv_user_regset[] = { .set = riscv_vr_set, }, #endif +#ifdef CONFIG_RISCV_USER_CFI + [REGSET_CFI] = { + .core_note_type = NT_RISCV_USER_CFI, + .align = sizeof(__u64), + .n = sizeof(struct user_cfi_state) / sizeof(__u64), + .size = sizeof(__u64), + .regset_get = riscv_cfi_get, + .set = riscv_cfi_set, + } +#endif };

static const struct user_regset_view riscv_user_native_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b9935988da5c..7ef63b2b67a1 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -450,6 +450,7 @@ typedef struct elf64_shdr { #define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ #define NT_RISCV_CSR 0x900 /* RISC-V Control and Status Registers */ #define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */ +#define NT_RISCV_USER_CFI 0x902 /* RISC-V shadow stack state */ #define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ #define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ #define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */

From: Clément Léger cleger@rivosinc.com

Add necessary SBI definitions to use the FWFT extension.

Signed-off-by: Clément Léger cleger@rivosinc.com --- arch/riscv/include/asm/sbi.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+)

diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 98f631b051db..754e5cdabf46 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -34,6 +34,7 @@ enum sbi_ext_id { SBI_EXT_PMU = 0x504D55, SBI_EXT_DBCN = 0x4442434E, SBI_EXT_STA = 0x535441, + SBI_EXT_FWFT = 0x46574654,

/* Experimentals extensions must lie within this range */ SBI_EXT_EXPERIMENTAL_START = 0x08000000, @@ -281,6 +282,32 @@ struct sbi_sta_struct {

#define SBI_SHMEM_DISABLE -1

+/* SBI function IDs for FW feature extension */ +#define SBI_EXT_FWFT_SET 0x0 +#define SBI_EXT_FWFT_GET 0x1 + +enum sbi_fwft_feature_t { + SBI_FWFT_MISALIGNED_EXC_DELEG = 0x0, + SBI_FWFT_LANDING_PAD = 0x1, + SBI_FWFT_SHADOW_STACK = 0x2, + SBI_FWFT_DOUBLE_TRAP = 0x3, + SBI_FWFT_PTE_AD_HW_UPDATING = 0x4, + SBI_FWFT_LOCAL_RESERVED_START = 0x5, + SBI_FWFT_LOCAL_RESERVED_END = 0x3fffffff, + SBI_FWFT_LOCAL_PLATFORM_START = 0x40000000, + SBI_FWFT_LOCAL_PLATFORM_END = 0x7fffffff, + + SBI_FWFT_GLOBAL_RESERVED_START = 0x80000000, + SBI_FWFT_GLOBAL_RESERVED_END = 0xbfffffff, + SBI_FWFT_GLOBAL_PLATFORM_START = 0xc0000000, + SBI_FWFT_GLOBAL_PLATFORM_END = 0xffffffff, +}; + +#define SBI_FWFT_GLOBAL_FEATURE_BIT (1 << 31) +#define SBI_FWFT_PLATFORM_FEATURE_BIT (1 << 30) + +#define SBI_FWFT_SET_FLAG_LOCK (1 << 0) + /* SBI spec version fields */ #define SBI_SPEC_VERSION_DEFAULT 0x1 #define SBI_SPEC_VERSION_MAJOR_SHIFT 24

This commit adds a kernel command line option using which user cfi can be disabled.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- arch/riscv/kernel/usercfi.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)

diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c index 40c32258b6ec..d92b49261b58 100644 --- a/arch/riscv/kernel/usercfi.c +++ b/arch/riscv/kernel/usercfi.c @@ -17,6 +17,8 @@ #include <asm/csr.h> #include <asm/usercfi.h>

+bool disable_riscv_usercfi; + #define SHSTK_ENTRY_SIZE sizeof(void *)

bool is_shstk_enabled(struct task_struct *task) @@ -393,6 +395,9 @@ int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status) unsigned long size = 0, addr = 0; bool enable_shstk = false;

+ if (disable_riscv_usercfi) + return 0; + if (!cpu_supports_shadow_stack()) return -EINVAL;

@@ -472,6 +477,9 @@ int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status) { bool enable_indir_lp = false;

+ if (disable_riscv_usercfi) + return 0; + if (!cpu_supports_indirect_br_lp_instr()) return -EINVAL;

@@ -504,3 +512,15 @@ int arch_lock_indir_br_lp_status(struct task_struct *task,

return 0; } + +static int __init setup_global_riscv_enable(char *str) +{ + if (strcmp(str, "true") == 0) + disable_riscv_usercfi = true; + + pr_info("Setting riscv usercfi to be %s\n", (disable_riscv_usercfi ? "disabled" : "enabled")); + + return 1; +} + +__setup("disable_riscv_usercfi=", setup_global_riscv_enable);

Adding documentation on landing pad aka indirect branch tracking on riscv and kernel interfaces exposed so that user tasks can enable it.

Signed-off-by: Deepak Gupta debug@rivosinc.com --- Documentation/arch/riscv/index.rst | 1 + Documentation/arch/riscv/zicfilp.rst | 115 +++++++++++++++++++++++++++++++++++ 2 files changed, 116 insertions(+)

diff --git a/Documentation/arch/riscv/index.rst b/Documentation/arch/riscv/index.rst index eecf347ce849..be7237b69682 100644 --- a/Documentation/arch/riscv/index.rst +++ b/Documentation/arch/riscv/index.rst @@ -14,6 +14,7 @@ RISC-V architecture uabi vector cmodx + zicfilp

features

diff --git a/Documentation/arch/riscv/zicfilp.rst b/Documentation/arch/riscv/zicfilp.rst new file mode 100644 index 000000000000..a188d78fcde6 --- /dev/null +++ b/Documentation/arch/riscv/zicfilp.rst @@ -0,0 +1,115 @@ +.. SPDX-License-Identifier: GPL-2.0 + +:Author: Deepak Gupta debug@rivosinc.com +:Date: 12 January 2024 + +==================================================== +Tracking indirect control transfers on RISC-V Linux +==================================================== + +This document briefly describes the interface provided to userspace by Linux +to enable indirect branch tracking for user mode applications on RISV-V + +1. Feature Overview +-------------------- + +Memory corruption issues usually result in to crashes, however when in hands of +an adversary and if used creatively can result into variety security issues. + +One of those security issues can be code re-use attacks on program where adversary +can use corrupt function pointers and chain them together to perform jump oriented +programming (JOP) or call oriented programming (COP) and thus compromising control +flow integrity (CFI) of the program. + +Function pointers live in read-write memory and thus are susceptible to corruption +and allows an adversary to reach any program counter (PC) in address space. On +RISC-V zicfilp extension enforces a restriction on such indirect control +transfers: + +- indirect control transfers must land on a landing pad instruction ``lpad``. + There are two exception to this rule: + + - rs1 = x1 or rs1 = x5, i.e. a return from a function and returns are + protected using shadow stack (see zicfiss.rst) + + - rs1 = x7. On RISC-V compiler usually does below to reach function + which is beyond the offset possible J-type instruction:: + + auipc x7, <imm> + jalr (x7) + + Such form of indirect control transfer are still immutable and don't rely + on memory and thus rs1=x7 is exempted from tracking and considered software + guarded jumps. + +``lpad`` instruction is pseudo of ``auipc rd, <imm_20bit>`` with ``rd=x0`` and +is a HINT nop. ``lpad`` instruction must be aligned on 4 byte boundary and +compares 20 bit immediate withx7. If ``imm_20bit`` == 0, CPU don't perform any +comparision with ``x7``. If ``imm_20bit`` != 0, then ``imm_20bit`` must match +``x7`` else CPU will raise ``software check exception`` (``cause=18``) with +``*tval = 2``. + +Compiler can generate a hash over function signatures and setup them (truncated +to 20bit) in x7 at callsites and function prologues can have ``lpad`` with same +function hash. This further reduces number of program counters a call site can +reach. + +2. ELF and psABI +----------------- + +Toolchain sets up :c:macro:`GNU_PROPERTY_RISCV_FEATURE_1_FCFI` for property +:c:macro:`GNU_PROPERTY_RISCV_FEATURE_1_AND` in notes section of the object file. + +3. Linux enabling +------------------ + +User space programs can have multiple shared objects loaded in its address space +and it's a difficult task to make sure all the dependencies have been compiled +with support of indirect branch. Thus it's left to dynamic loader to enable +indirect branch tracking for the program. + +4. prctl() enabling +-------------------- + +:c:macro:`PR_SET_INDIR_BR_LP_STATUS` / :c:macro:`PR_GET_INDIR_BR_LP_STATUS` / +:c:macro:`PR_LOCK_INDIR_BR_LP_STATUS` are three prctls added to manage indirect +branch tracking. prctls are arch agnostic and returns -EINVAL on other arches. + +* prctl(PR_SET_INDIR_BR_LP_STATUS, unsigned long arg) + +If arg1 is :c:macro:`PR_INDIR_BR_LP_ENABLE` and if CPU supports ``zicfilp`` +then kernel will enabled indirect branch tracking for the task. Dynamic loader +can issue this :c:macro:`prctl` once it has determined that all the objects +loaded in address space support indirect branch tracking. Additionally if there +is a `dlopen` to an object which wasn't compiled with ``zicfilp``, dynamic +loader can issue this prctl with arg1 set to 0 (i.e. +:c:macro:`PR_INDIR_BR_LP_ENABLE` being clear) + +* prctl(PR_GET_INDIR_BR_LP_STATUS, unsigned long arg) + +Returns current status of indirect branch tracking. If enabled it'll return +:c:macro:`PR_INDIR_BR_LP_ENABLE` + +* prctl(PR_LOCK_INDIR_BR_LP_STATUS, unsigned long arg) + +Locks current status of indirect branch tracking on the task. User space may +want to run with strict security posture and wouldn't want loading of objects +without ``zicfilp`` support in it and thus would want to disallow disabling of +indirect branch tracking. In that case user space can use this prctl to lock +current settings. + +5. violations related to indirect branch tracking +-------------------------------------------------- + +Pertaining to indirect branch tracking, CPU raises software check exception in +following conditions: + +- missing ``lpad`` after indirect call / jmp +- ``lpad`` not on 4 byte boundary +- ``imm_20bit`` embedded in ``lpad`` instruction doesn't match with ``x7`` + +In all 3 cases, ``*tval = 2`` is captured and software check exception is +raised (``cause=18``) + +Linux kernel will treat this as :c:macro:`SIGSEV`` with code = +:c:macro:`SEGV_CPERR` and follow normal course of signal delivery.

Adds kselftest for RISC-V control flow integrity implementation for user mode. There is not a lot going on in kernel for enabling landing pad for user mode. cfi selftest are intended to be compiled with zicfilp and zicfiss enabled compiler. Thus kselftest simply checks if landing pad and shadow stack for the binary and process are enabled or not. selftest then register a signal handler for SIGSEGV. Any control flow violation are reported as SIGSEGV with si_code = SEGV_CPERR. Test will fail on receiving any SEGV_CPERR. Shadow stack part has more changes in kernel and thus there are separate tests for that - Exercise `map_shadow_stack` syscall - `fork` test to make sure COW works for shadow stack pages - gup tests As of today kernel uses FOLL_FORCE when access happens to memory via /proc/<pid>/mem. Not breaking that for shadow stack - signal test. Make sure signal delivery results in token creation on shadow stack and consumes (and verifies) token on sigreturn - shadow stack protection test. attempts to write using regular store instruction on shadow stack memory must result in access faults

Signed-off-by: Deepak Gupta debug@rivosinc.com --- tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/cfi/.gitignore | 3 + tools/testing/selftests/riscv/cfi/Makefile | 10 + tools/testing/selftests/riscv/cfi/cfi_rv_test.h | 83 +++++ tools/testing/selftests/riscv/cfi/riscv_cfi_test.c | 82 +++++ tools/testing/selftests/riscv/cfi/shadowstack.c | 362 +++++++++++++++++++++ tools/testing/selftests/riscv/cfi/shadowstack.h | 37 +++ 7 files changed, 578 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index 7ce03d832b64..6e142fe004ab 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not)

ifneq (,$(filter $(ARCH),riscv)) -RISCV_SUBTARGETS ?= hwprobe vector mm sigreturn +RISCV_SUBTARGETS ?= hwprobe vector mm sigreturn cfi else RISCV_SUBTARGETS := endif diff --git a/tools/testing/selftests/riscv/cfi/.gitignore b/tools/testing/selftests/riscv/cfi/.gitignore new file mode 100644 index 000000000000..ce7623f9da28 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/.gitignore @@ -0,0 +1,3 @@ +cfitests +riscv_cfi_test +shadowstack \ No newline at end of file diff --git a/tools/testing/selftests/riscv/cfi/Makefile b/tools/testing/selftests/riscv/cfi/Makefile new file mode 100644 index 000000000000..b65f7ff38a32 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/Makefile @@ -0,0 +1,10 @@ +CFLAGS += -I$(top_srcdir)/tools/include + +CFLAGS += -march=rv64gc_zicfilp_zicfiss + +TEST_GEN_PROGS := cfitests + +include ../../lib.mk + +$(OUTPUT)/cfitests: riscv_cfi_test.c shadowstack.c + $(CC) -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/cfi/cfi_rv_test.h b/tools/testing/selftests/riscv/cfi/cfi_rv_test.h new file mode 100644 index 000000000000..fa1cf7183672 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/cfi_rv_test.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef SELFTEST_RISCV_CFI_H +#define SELFTEST_RISCV_CFI_H +#include <stddef.h> +#include <sys/types.h> +#include "shadowstack.h" + +#define RISCV_CFI_SELFTEST_COUNT RISCV_SHADOW_STACK_TESTS + +#define CHILD_EXIT_CODE_SSWRITE 10 +#define CHILD_EXIT_CODE_SIG_TEST 11 + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + register long _arg4 __asm__ ("a3") = (long)(arg4); \ + register long _arg5 __asm__ ("a4") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("a7") = (num); \ + register long _arg1 __asm__ ("a0") = (long)(arg1); \ + register long _arg2 __asm__ ("a1") = (long)(arg2); \ + register long _arg3 __asm__ ("a2") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "ecall\n" \ + : "+r"(_arg1) \ + : "r"(_arg2), "r"(_arg3), \ + "r"(_num) \ + : "memory", "cc" \ + ); \ + _arg1; \ +}) + +#ifndef __NR_prctl +#define __NR_prctl 167 +#endif + +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 453 +#endif + +#define CSR_SSP 0x011 + +#ifdef __ASSEMBLY__ +#define __ASM_STR(x) x +#else +#define __ASM_STR(x) #x +#endif + +#define csr_read(csr) \ +({ \ + register unsigned long __v; \ + __asm__ __volatile__ ("csrr %0, " __ASM_STR(csr) \ + : "=r" (__v) : \ + : "memory"); \ + __v; \ +}) + +#define csr_write(csr, val) \ +({ \ + unsigned long __v = (unsigned long) (val); \ + __asm__ __volatile__ ("csrw " __ASM_STR(csr) ", %0" \ + : : "rK" (__v) \ + : "memory"); \ +}) + +#endif diff --git a/tools/testing/selftests/riscv/cfi/riscv_cfi_test.c b/tools/testing/selftests/riscv/cfi/riscv_cfi_test.c new file mode 100644 index 000000000000..f22b3f0f24de --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/riscv_cfi_test.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../../kselftest.h" +#include <signal.h> +#include <asm/ucontext.h> +#include <linux/prctl.h> +#include "cfi_rv_test.h" + +/* do not optimize cfi related test functions */ +#pragma GCC push_options +#pragma GCC optimize("O0") + +void sigsegv_handler(int signum, siginfo_t *si, void *uc) +{ + struct ucontext *ctx = (struct ucontext *) uc; + + if (si->si_code == SEGV_CPERR) { + printf("Control flow violation happened somewhere\n"); + printf("pc where violation happened %lx\n", ctx->uc_mcontext.gregs[0]); + exit(-1); + } + + printf("In sigsegv handler\n"); + /* all other cases are expected to be of shadow stack write case */ + exit(CHILD_EXIT_CODE_SSWRITE); +} + +bool register_signal_handler(void) +{ + struct sigaction sa = {}; + + sa.sa_sigaction = sigsegv_handler; + sa.sa_flags = SA_SIGINFO; + if (sigaction(SIGSEGV, &sa, NULL)) { + printf("registering signal handler for landing pad violation failed\n"); + return false; + } + + return true; +} + +int main(int argc, char *argv[]) +{ + int ret = 0; + unsigned long lpad_status = 0, ss_status = 0; + + ksft_print_header(); + + ksft_set_plan(RISCV_CFI_SELFTEST_COUNT); + + ksft_print_msg("starting risc-v tests\n"); + + /* + * Landing pad test. Not a lot of kernel changes to support landing + * pad for user mode except lighting up a bit in senvcfg via a prctl + * Enable landing pad through out the execution of test binary + */ + ret = my_syscall5(__NR_prctl, PR_GET_INDIR_BR_LP_STATUS, &lpad_status, 0, 0, 0); + if (ret) + ksft_exit_skip("Get landing pad status failed with %d\n", ret); + + if (!(lpad_status & PR_INDIR_BR_LP_ENABLE)) + ksft_exit_skip("landing pad is not enabled, should be enabled via glibc\n"); + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &ss_status, 0, 0, 0); + if (ret) + ksft_exit_skip("Get shadow stack failed with %d\n", ret); + + if (!(ss_status & PR_SHADOW_STACK_ENABLE)) + ksft_exit_skip("shadow stack is not enabled, should be enabled via glibc\n"); + + if (!register_signal_handler()) + ksft_exit_skip("registering signal handler for SIGSEGV failed\n"); + + ksft_print_msg("landing pad and shadow stack are enabled for binary\n"); + ksft_print_msg("starting risc-v shadow stack tests\n"); + execute_shadow_stack_tests(); + + ksft_finished(); +} + +#pragma GCC pop_options diff --git a/tools/testing/selftests/riscv/cfi/shadowstack.c b/tools/testing/selftests/riscv/cfi/shadowstack.c new file mode 100644 index 000000000000..2f65eb970c44 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/shadowstack.c @@ -0,0 +1,362 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../../kselftest.h" +#include <sys/wait.h> +#include <signal.h> +#include <fcntl.h> +#include <asm-generic/unistd.h> +#include <sys/mman.h> +#include "shadowstack.h" +#include "cfi_rv_test.h" + +/* do not optimize shadow stack related test functions */ +#pragma GCC push_options +#pragma GCC optimize("O0") + +void zar(void) +{ + unsigned long ssp = 0; + + ssp = csr_read(CSR_SSP); + printf("inside %s and shadow stack ptr is %lx\n", __func__, ssp); +} + +void bar(void) +{ + printf("inside %s\n", __func__); + zar(); +} + +void foo(void) +{ + printf("inside %s\n", __func__); + bar(); +} + +void zar_child(void) +{ + unsigned long ssp = 0; + + ssp = csr_read(CSR_SSP); + printf("inside %s and shadow stack ptr is %lx\n", __func__, ssp); +} + +void bar_child(void) +{ + printf("inside %s\n", __func__); + zar_child(); +} + +void foo_child(void) +{ + printf("inside %s\n", __func__); + bar_child(); +} + +typedef void (call_func_ptr)(void); +/* + * call couple of functions to test push pop. + */ +int shadow_stack_call_tests(call_func_ptr fn_ptr, bool parent) +{ + if (parent) + printf("call test for parent\n"); + else + printf("call test for child\n"); + + (fn_ptr)(); + + return 0; +} + +/* forks a thread, and ensure shadow stacks fork out */ +bool shadow_stack_fork_test(unsigned long test_num, void *ctx) +{ + int pid = 0, child_status = 0, parent_pid = 0, ret = 0; + unsigned long ss_status = 0; + + printf("exercising shadow stack fork test\n"); + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &ss_status, 0, 0, 0); + if (ret) { + printf("shadow stack get status prctl failed with errorcode %d\n", ret); + return false; + } + + if (!(ss_status & PR_SHADOW_STACK_ENABLE)) + ksft_exit_skip("shadow stack is not enabled, should be enabled via glibc\n"); + + parent_pid = getpid(); + pid = fork(); + + if (pid) { + printf("Parent pid %d and child pid %d\n", parent_pid, pid); + shadow_stack_call_tests(&foo, true); + } else + shadow_stack_call_tests(&foo_child, false); + + if (pid) { + printf("waiting on child to finish\n"); + wait(&child_status); + } else { + /* exit child gracefully */ + exit(0); + } + + if (pid && WIFSIGNALED(child_status)) { + printf("child faulted"); + return false; + } + + return true; +} + +/* exercise `map_shadow_stack`, pivot to it and call some functions to ensure it works */ +#define SHADOW_STACK_ALLOC_SIZE 4096 +bool shadow_stack_map_test(unsigned long test_num, void *ctx) +{ + unsigned long shdw_addr; + int ret = 0; + + shdw_addr = my_syscall3(__NR_map_shadow_stack, NULL, SHADOW_STACK_ALLOC_SIZE, 0); + + if (((long) shdw_addr) <= 0) { + printf("map_shadow_stack failed with error code %d\n", (int) shdw_addr); + return false; + } + + ret = munmap((void *) shdw_addr, SHADOW_STACK_ALLOC_SIZE); + + if (ret) { + printf("munmap failed with error code %d\n", ret); + return false; + } + + return true; +} + +/* + * shadow stack protection tests. map a shadow stack and + * validate all memory protections work on it + */ +bool shadow_stack_protection_test(unsigned long test_num, void *ctx) +{ + unsigned long shdw_addr; + unsigned long *write_addr = NULL; + int ret = 0, pid = 0, child_status = 0; + + shdw_addr = my_syscall3(__NR_map_shadow_stack, NULL, SHADOW_STACK_ALLOC_SIZE, 0); + + if (((long) shdw_addr) <= 0) { + printf("map_shadow_stack failed with error code %d\n", (int) shdw_addr); + return false; + } + + write_addr = (unsigned long *) shdw_addr; + pid = fork(); + + /* no child was created, return false */ + if (pid == -1) + return false; + + /* + * try to perform a store from child on shadow stack memory + * it should result in SIGSEGV + */ + if (!pid) { + /* below write must lead to SIGSEGV */ + *write_addr = 0xdeadbeef; + } else { + wait(&child_status); + } + + /* test fail, if 0xdeadbeef present on shadow stack address */ + if (*write_addr == 0xdeadbeef) { + printf("write suceeded\n"); + return false; + } + + /* if child reached here, then fail */ + if (!pid) { + printf("child reached unreachable state\n"); + return false; + } + + /* if child exited via signal handler but not for write on ss */ + if (WIFEXITED(child_status) && + WEXITSTATUS(child_status) != CHILD_EXIT_CODE_SSWRITE) { + printf("child wasn't signaled for write on shadow stack\n"); + return false; + } + + ret = munmap(write_addr, SHADOW_STACK_ALLOC_SIZE); + if (ret) { + printf("munmap failed with error code %d\n", ret); + return false; + } + + return true; +} + +#define SS_MAGIC_WRITE_VAL 0xbeefdead + +int gup_tests(int mem_fd, unsigned long *shdw_addr) +{ + unsigned long val = 0; + + lseek(mem_fd, (unsigned long)shdw_addr, SEEK_SET); + if (read(mem_fd, &val, sizeof(val)) < 0) { + printf("reading shadow stack mem via gup failed\n"); + return 1; + } + + val = SS_MAGIC_WRITE_VAL; + lseek(mem_fd, (unsigned long)shdw_addr, SEEK_SET); + if (write(mem_fd, &val, sizeof(val)) < 0) { + printf("writing shadow stack mem via gup failed\n"); + return 1; + } + + if (*shdw_addr != SS_MAGIC_WRITE_VAL) { + printf("GUP write to shadow stack memory didn't happen\n"); + return 1; + } + + return 0; +} + +bool shadow_stack_gup_tests(unsigned long test_num, void *ctx) +{ + unsigned long shdw_addr = 0; + unsigned long *write_addr = NULL; + int fd = 0; + bool ret = false; + + shdw_addr = my_syscall3(__NR_map_shadow_stack, NULL, SHADOW_STACK_ALLOC_SIZE, 0); + + if (((long) shdw_addr) <= 0) { + printf("map_shadow_stack failed with error code %d\n", (int) shdw_addr); + return false; + } + + write_addr = (unsigned long *) shdw_addr; + + fd = open("/proc/self/mem", O_RDWR); + if (fd == -1) + return false; + + if (gup_tests(fd, write_addr)) { + printf("gup tests failed\n"); + goto out; + } + + ret = true; +out: + if (shdw_addr && munmap(write_addr, SHADOW_STACK_ALLOC_SIZE)) { + printf("munmap failed with error code %d\n", ret); + ret = false; + } + + return ret; +} + +volatile bool break_loop; + +void sigusr1_handler(int signo) +{ + printf("In sigusr1 handler\n"); + break_loop = true; +} + +bool sigusr1_signal_test(void) +{ + struct sigaction sa = {}; + + sa.sa_handler = sigusr1_handler; + sa.sa_flags = 0; + sigemptyset(&sa.sa_mask); + if (sigaction(SIGUSR1, &sa, NULL)) { + printf("registering signal handler for SIGUSR1 failed\n"); + return false; + } + + return true; +} +/* + * shadow stack signal test. shadow stack must be enabled. + * register a signal, fork another thread which is waiting + * on signal. Send a signal from parent to child, verify + * that signal was received by child. If not test fails + */ +bool shadow_stack_signal_test(unsigned long test_num, void *ctx) +{ + int pid = 0, child_status = 0, ret = 0; + unsigned long ss_status = 0; + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &ss_status, 0, 0, 0); + if (ret) { + printf("shadow stack get status prctl failed with errorcode %d\n", ret); + return false; + } + + if (!(ss_status & PR_SHADOW_STACK_ENABLE)) + ksft_exit_skip("shadow stack is not enabled, should be enabled via glibc\n"); + + /* this should be caught by signal handler and do an exit */ + if (!sigusr1_signal_test()) { + printf("registering sigusr1 handler failed\n"); + exit(-1); + } + + pid = fork(); + + if (pid == -1) { + printf("signal test: fork failed\n"); + goto out; + } + + if (pid == 0) { + while (!break_loop) + sleep(1); + + exit(11); + /* child shouldn't go beyond here */ + } + + /* send SIGUSR1 to child */ + kill(pid, SIGUSR1); + wait(&child_status); + +out: + + return (WIFEXITED(child_status) && + WEXITSTATUS(child_status) == 11); +} + +int execute_shadow_stack_tests(void) +{ + int ret = 0; + unsigned long test_count = 0; + unsigned long shstk_status = 0; + + printf("Executing RISC-V shadow stack self tests\n"); + + ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &shstk_status, 0, 0, 0); + + if (ret != 0) + ksft_exit_skip("Get shadow stack status failed with %d\n", ret); + + /* + * If we are here that means get shadow stack status succeeded and + * thus shadow stack support is baked in the kernel. + */ + while (test_count < ARRAY_SIZE(shstk_tests)) { + ksft_test_result((*shstk_tests[test_count].t_func)(test_count, NULL), + shstk_tests[test_count].name); + test_count++; + } + + return 0; +} + +#pragma GCC pop_options diff --git a/tools/testing/selftests/riscv/cfi/shadowstack.h b/tools/testing/selftests/riscv/cfi/shadowstack.h new file mode 100644 index 000000000000..b43e74136a26 --- /dev/null +++ b/tools/testing/selftests/riscv/cfi/shadowstack.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef SELFTEST_SHADOWSTACK_TEST_H +#define SELFTEST_SHADOWSTACK_TEST_H +#include <stddef.h> +#include <linux/prctl.h> + +/* + * a cfi test returns true for success or false for fail + * takes a number for test number to index into array and void pointer. + */ +typedef bool (*shstk_test_func)(unsigned long test_num, void *); + +struct shadow_stack_tests { + char *name; + shstk_test_func t_func; +}; + +bool shadow_stack_fork_test(unsigned long test_num, void *ctx); +bool shadow_stack_map_test(unsigned long test_num, void *ctx); +bool shadow_stack_protection_test(unsigned long test_num, void *ctx); +bool shadow_stack_gup_tests(unsigned long test_num, void *ctx); +bool shadow_stack_signal_test(unsigned long test_num, void *ctx); + +static struct shadow_stack_tests shstk_tests[] = { + { "shstk fork test\n", shadow_stack_fork_test }, + { "map shadow stack syscall\n", shadow_stack_map_test }, + { "shadow stack gup tests\n", shadow_stack_gup_tests }, + { "shadow stack signal tests\n", shadow_stack_signal_test}, + { "memory protections of shadow stack memory\n", shadow_stack_protection_test } +}; + +#define RISCV_SHADOW_STACK_TESTS ARRAY_SIZE(shstk_tests) + +int execute_shadow_stack_tests(void); + +#endif